© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29211
    Prev
    Next
    INDEX
    Explanations

    listing numbers or choices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Õµ
    -0.07
     kou
    -0.07
    åĸľè¿İ
    -0.07
    æĭ¿
    -0.06
    å°Ķ
    -0.06
     past
    -0.06
    _RUNTIME
    -0.06
    èģļä¼ļ
    -0.06
    é¢Ħ
    -0.06
    apul
    -0.06
    POSITIVE LOGITS
    oser
    0.08
    eram
    0.08
    æĻ
    0.07
    íĦ´
    0.07
    éĺª
    0.07
    .Strict
    0.07
    Ùĩد
    0.07
    $c
    0.07
    åĴĮæĮĩ导
    0.06
    enna
    0.06
    Activations Density 0.002%

    No Known Activations